Kimi K2 Thinking
Open-weights chat model from Kimi. One API key reaches all 3 providers, with automatic failover.
No card required. Start with 1 million free tokens.
About Kimi K2 Thinking
Kimi K2 Thinking is an open-weights chat model published by Kimi, with a 262,144-token context window. It scores 91 on AI IQ, ranked #159. Through TrustedRouter it runs on 3 providers, with options in the US, from $0.63 per million input tokens.
- Model ID
moonshotai/kimi-k2-thinking- Publisher
- Kimi
- Modes
- chat
- Billing
- Credits or your own provider key
Set it up with your agent
Paste this into Claude Code, Cursor or any coding agent.
Use Kimi K2 Thinking through TrustedRouter in this project.
1. Read https://trustedrouter.com/llms.txt
2. Point the OpenAI-compatible client at
https://api.trustedrouter.com/v1 and read the key from
TRUSTEDROUTER_API_KEY.
3. Set the model to moonshotai/kimi-k2-thinking.
4. Run the tests, then show me the diff before committing.import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.trustedrouter.com/v1",
api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
response = client.chat.completions.create(
model="moonshotai/kimi-k2-thinking",
messages=[{"role": "user", "content": "What is the capital of France?"}],
)
print(response.choices[0].message.content)curl https://api.trustedrouter.com/v1/chat/completions \
-H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k2-thinking",
"messages": [{"role": "user", "content": "What is the capital of France?"}]
}'Providers
Your key goes to the cheapest healthy provider and fails over on its own. Open a row for retention, location and weight format, or see how we check privacy claims and the live speed leaderboard.
| Provider | Input | Cached | Output | Cost per 1M in + out | Details |
|---|---|---|---|---|---|
Amazon Bedrock
|
$0.633 | — | $2.64 | $3.27 | |
|
Retention Retention unverified - not strict ZDR: This exact model and upstream ID have not been approved for strict ZDR under the current account controls. Provider-wide ZDR, no-training and successful inference are insufficient. Safety retention or other content storage may apply; the route is excluded until reviewed. This exact model and upstream ID have not been approved for strict ZDR under the current account controls. Provider-wide ZDR, no-training and successful inference are insufficient. Safety retention or other content storage may apply; the route is excluded until reviewed. Location Operator country: US Headquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. Weight format Unknown Price and speed Input $0.633/1M · Cached input Not published · Output $2.6375/1M TTFT: 1.06 s Speed: insufficient data Last sample: |
|||||
IO Intelligence
|
$0.633 | $0.316 | $2.64 | $3.27 | |
|
Retention Verification: privacy unknown. In its September 28, 2026 marketplace submission, io.net states that inference prompts and completions are processed only in memory, are not stored or logged, and are not used for training. Content-free operational metadata is retained for billing, capacity planning and abuse prevention. This is a provider declaration: the reviewed public privacy policy does not establish inference-specific zero-retention terms, and the applicable DPA has not been reviewed. Routes remain Standard pending that evidence. Confidential compute is offered on request, but this integration has no verified confidential-compute or provider-side E2EE guarantee. Location Operator country: US Headquarters / registered office: West Hollywood, California, United States (operating address). Company location source (reviewed 2026-09-28). Inference: United States and Canada, provider-declared; no US-only or fixed-country guarantee on this route. io.net declares US and Canadian serving locations and data residency in its September 28, 2026 marketplace submission. This is provider-wide information, not an independently verified per-model or per-request location. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-28. API documentation (not a location guarantee) Weight format Unknown Price and speed Input $0.633/1M · Cached input $0.3165/1M · Output $2.6375/1M TTFT: insufficient data Speed: insufficient data Last sample: |
|||||
Novita AI
|
$0.633 | $0.158 | $2.64 | $3.27 | |
|
Retention Verification: privacy unknown. No provider-ZDR claim is tracked here. Novita's privacy policy says personal information is not used for model training; customer-content processing is governed by customer agreements. Location Operator country: US Headquarters / registered office: San Francisco, California, United States. Company location source (reviewed 2026-09-27). Inference: Shared inference API; processing countries unconfirmed, no fixed-region commitment. No exhaustive inference-country list verified for the shared model API. Novita publishes worldwide GPU rental regions, but that separate product does not establish shared serverless model placement. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-10-28. Weight format Unknown Price and speed Input $0.633/1M · Cached input $0.15825/1M · Output $2.6375/1M TTFT: insufficient data Speed: insufficient data |
|||||
Append :nitro to the model ID, or send "provider": {"sort": "throughput"}, to route to the fastest provider instead.
Questions
What model ID should I use for Kimi K2 Thinking?
Use moonshotai/kimi-k2-thinking as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Do you log my prompts or outputs?
No. Prompt and output content are intentionally excluded from the control plane and metadata systems. Optional content export requires explicit destination-level configuration.
Which providers serve Kimi K2 Thinking?
TrustedRouter currently lists Novita AI, IO Intelligence, and Amazon Bedrock for Kimi K2 Thinking. Provider availability and routing eligibility can change as catalog and health data update.
How much does Kimi K2 Thinking cost through TrustedRouter?
The current lowest Credits input price is $0.633/1M and the lowest Credits output price is $2.6375/1M. Prices are per one million tokens and come from the current route catalog.
How do I require zero data retention for Kimi K2 Thinking?
Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.
Kimi K2 Thinking vs other models
Start building with Kimi K2 Thinking.
No card required. Start with 1 million free tokens.